Learning to detect chest radiographs containing lung nodules using visual attention networks

Abstract

Machine learning approaches hold great potential for the automated detection of lung nodules in chest radiographs, but training the algorithms requires vary large amounts of manually annotated images, which are difficult to obtain. Weak labels indicating whether a radiograph is likely to contain pulmonary nodules are typically easier to obtain at scale by parsing historical free-text radiological reports associated to the radiographs. Using a repositotory of over 700,000 chest radiographs, in this study we demonstrate that promising nodule detection performance can be achieved using weak labels through convolutional neural networks for radiograph classification. We propose two network architectures for the classification of images likely to contain pulmonary nodules using both weak labels and manually-delineated bounding boxes, when these are available. Annotated nodules are used at training time to deliver a visual attention mechanism informing the model about its localisation performance. The first architecture extracts saliency maps from high-level convolutional layers and compares the estimated position of a nodule against the ground truth, when this is available. A corresponding localisation error is then back-propagated along with the softmax classification error. The second approach consists of a recurrent attention model that learns to observe a short sequence of smaller image portions through reinforcement learning. When a nodule annotation is available at training time, the reward function is modified accordingly so that exploring portions of the radiographs away from a nodule incurs a larger penalty. Our empirical results demonstrate the potential advantages of these architectures in comparison to competing methodologies.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• A Survey on Deep Learning in Medical Image Analysis
• ADADELTA: An Adaptive Learning Rate Method
• Recurrent Models of Visual Attention
• Multiple Object Recognition with Visual Attention
• Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
• Deep Learning is Robust to Massive Label Noise
• How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?
• Attention for Fine-Grained Categorization
• Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels
• Interleaved Text/Image Deep Mining on a Large-Scale Radiology Database for Automated Image Interpretation
• On Learning Where To Look
• Learning what to look in chest X-rays with a recurrent visual attention model
• Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
• Deep Learning from Noisy Image Labels with Quality Embedding

Cited by in corpus (20)

• Explainable artificial intelligence (XAI) in deep learning-based medical image analysis
• Deep Learning for Chest X-ray Analysis: A Survey
• Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
• A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
• Shape and Margin-Aware Lung Nodule Classification in Low-dose CT Images via Soft Activation Mapping
• Deep Metric Learning-based Image Retrieval System for Chest Radiograph and its Clinical Applications in COVID-19
• An attention-based multi-resolution model for prostate whole slide imageclassification and localization
• Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels
• Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detection
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• COVIDX: Computer-aided diagnosis of Covid-19 and its severity prediction with raw digital chest X-ray images
• Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
• Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray images
• A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
• Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition
• Cross Chest Graph for Disease Diagnosis with Structural Relational Reasoning
• LU-Net: a multi-task network to improve the robustness of segmentation of left ventriclular structures by deep learning in 2D echocardiography